Table 3.

Cross-domain validation results comparing industrial machinery and battery RUL prediction performance.

Result	Model	RMSE	MSE	MAE		MAPE
Without filter	CNN	12.444	154.797	3.403	0.696	90.41
	LSTM	11.130	123.876	4.128	0.756	88.33
Kalman filter	CNN	9.096	82.735	1.605	0.837	92.49
	LSTM	9.645	93.030	3.724	0.817	89.13
Savitzky-Golay	CNN	3.913	15.310	0.686	0.969	97.50
	LSTM	9.868	97.372	2.792	0.808	90.30